INDEX

Explanations

programming syntax and structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.17

-bin

-0.16

 Grave

-0.15

acco

-0.15

åĩ¡

-0.15

 Seats

-0.15

-0.14

aca

-0.14

 Scatter

-0.14

outh

-0.14

POSITIVE LOGITS

uitka

0.17

utex

0.16

uptools

0.15

ÅĻÃŃÅ¾

0.15

ackbar

0.15

 compuls

0.15

warts

0.15

imetype

0.15

gne

0.15

Ã¤tz

0.15

Activations Density 0.056%

programming syntax and structures

No Comments

No Known Activations